{"total":62,"rows":[{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117,"area":null},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110,"area":null},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106,"area":null},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63,"area":null},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59,"area":null},{"id":"2405.16039","title":"MoEUT: Mixture-of-Experts Universal Transformers","created":"2024-05-25","cited_by_count":59,"area":"moe"},{"id":"2311.14737","title":"Positional Description Matters for Transformers Arithmetic","created":"2023-11-22","cited_by_count":56,"area":null},{"id":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2202.05780","title":"A Modern Self-Referential Weight Matrix That Learns to Modify Itself","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2312.07987","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention","created":"2023-12-13","cited_by_count":34,"area":"moe"},{"id":"2505.16381","title":"PaTH Attention: Position Encoding via Accumulating Householder Transformations","created":"2025-05-22","cited_by_count":34,"area":null},{"id":"2207.04785","title":"SALSA: Attacking Lattice Cryptography with Transformers","created":"2022-07-11","cited_by_count":28,"area":null},{"id":"2412.09616","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","created":"2024-12-12","cited_by_count":28,"area":"mllm"},{"id":"2310.10837","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","created":"2023-10-16","cited_by_count":27,"area":null},{"id":"2310.09753","title":"When can transformers reason with abstract symbols?","created":"2023-10-15","cited_by_count":24,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2210.00400","title":"Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks","created":"2022-10-02","cited_by_count":19,"area":null},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2305.03796","title":"Transformer Working Memory Enables Regular Language Reasoning and Natural Language Length Extrapolation","created":"2023-05-05","cited_by_count":13,"area":null},{"id":"2410.17980","title":"Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2502.04375","title":"An Analysis for Reasoning Bias of Language Models with Small Initialization","created":"2025-02-05","cited_by_count":13,"area":"lr"},{"id":"2210.06350","title":"CTL++: Evaluating Generalization on Never-Seen Compositional Patterns of Known Functions, and Compatibility of Neural Representations","created":"2022-10-12","cited_by_count":12,"area":null},{"id":"2604.21254","title":"Hyperloop Transformers","created":"2026-04-23","cited_by_count":12,"area":null},{"id":"2303.04178","title":"SALSA PICANTE: a machine learning attack on LWE with binary secrets","created":"2023-03-07","cited_by_count":11,"area":null},{"id":"2310.11984","title":"From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2506.21103","title":"Learning to Skip the Middle Layers of Transformers","created":"2025-06-26","cited_by_count":10,"area":"moe"},{"id":"2509.10534","title":"Decoupling the \"What\" and \"Where\" With Polar Coordinate Positional Embeddings","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2402.17396","title":"Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2502.16792","title":"The Role of Sparsity for Length Generalization in Transformers","created":"2025-02-24","cited_by_count":8,"area":null},{"id":"2305.19999","title":"Beam Tree Recursive Cells","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2409.07154","title":"Recurrent Aggregators in Neural Algorithmic Reasoning","created":"2024-09-11","cited_by_count":6,"area":null},{"id":"2501.00659","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2305.16954","title":"Compositional Generalization without Trees using Multiset Tagging and Latent Permutations","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2402.00976","title":"Investigating Recurrent Transformers with Dynamic Halt","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2604.13386","title":"Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling","created":"2026-04-15","cited_by_count":4,"area":"alignment"},{"id":"2305.02386","title":"Approximating CKY with Transformers","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2311.08695","title":"Attribute Diversity Determines the Systematicity Gap in VQA","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2406.06588","title":"Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models","created":"2024-06-05","cited_by_count":3,"area":"lr"},{"id":"2410.10596","title":"Overcoming classic challenges for artificial neural networks by providing incentives and practice","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2402.17407","title":"A Neural Rewriting System to Solve Algorithmic Problems","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2406.01012","title":"Attention-based Iterative Decomposition for Tensor Product Representation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2110.09138","title":"State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2302.05448","title":"The Construction of Reality in an AI: A Review","created":"2023-02-03","cited_by_count":1,"area":null},{"id":"2306.17249","title":"A Hybrid System for Systematic Generalization in Simple Arithmetic Problems","created":"2023-06-29","cited_by_count":1,"area":"lr"},{"id":"2409.01531","title":"On the Design Space Between Transformers and Recursive Neural Nets","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2502.17513","title":"Int2Int: a framework for mathematics with transformers","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2503.23174","title":"TRA: Better Length Generalisation with Threshold Relative Attention","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2603.05573","title":"Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View","created":"2026-03-05","cited_by_count":1,"area":"ssm"},{"id":"2401.07993","title":"Carrying over algorithm in transformers","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2408.00508","title":"Block-Operations: Using Modular Routing to Improve Compositional Generalization","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2504.15349","title":"Exploring Compositional Generalization (in COGS/ReCOGS_pos) by Transformers using Restricted Access Sequence Processing (RASP)","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2507.19372","title":"Learning neuro-symbolic convergent term rewriting systems","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.01267","title":"Iterative In-Context Learning to Enhance LLMs Abstract Reasoning: The Case-Study of Algebraic Tasks","created":"2025-09-01","cited_by_count":0,"area":"lr"},{"id":"2605.12578","title":"Recurrent Transformer-Based Near- and Far-Field THz Wideband Channel Estimation for UM-MIMO","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.31067","title":"Universal Transformers for Circuit Computations: Perfect Length Generalization in Tiny Transformers","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.34977","title":"SPIDER: Multi-Layer Semantic Token Pruning and Adaptive Sub-Layer Skipping in Multimodal Large Language Models","created":"2026-09-28","cited_by_count":0,"area":"mllm"}],"next_cursor":null}